CN114298817B - Training method and device for personal loan amount assessment model based on blockchain - Google Patents
Training method and device for personal loan amount assessment model based on blockchainInfo
- Publication number
- CN114298817B CN114298817B CN202111245698.XA CN202111245698A CN114298817B CN 114298817 B CN114298817 B CN 114298817B CN 202111245698 A CN202111245698 A CN 202111245698A CN 114298817 B CN114298817 B CN 114298817B
- Authority
- CN
- China
- Prior art keywords
- training
- node
- participating
- information
- central
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a training method and a training device for a personal loan amount evaluation model based on a blockchain, wherein the method comprises the steps that each training node writes respective training information into the blockchain according to training invitation sent by a task issuing node; the method comprises the steps that a task issuing node determines one of a plurality of training nodes to serve as a central training node according to training information of each training node, sends training tasks to the central training node and the rest of the training nodes to serve as participating training nodes, the central training node divides the training tasks into a plurality of training subtasks according to training capability information of each participating training node, distributes each training subtask to the corresponding participating training node to enable each participating training node to train, and the central training node obtains a personal loan amount assessment model through integration. The application can coordinate a plurality of participants to build a personal loan amount evaluation model together on the premise of not revealing the privacy data of the clients.
Description
Technical Field
The application relates to the technical field of computers, in particular to a training method and device of a personal loan amount evaluation model based on a blockchain.
Background
The drawing of the amount that the individual can maximally loan requires comprehensive consideration of multi-party information including individual deposit information, individual loan information, individual purchasing power information, individual medical and health information, individual basic information, and the like, which are stored in various departments or enterprises. Because each department or enterprise is not revealed in order to guarantee the citizen privacy, it is difficult to share with each bank information. Enterprises and business departments such as banks, financial institutions, hospitals and the like are also reluctant to disclose relevant data in order to protect customer privacy or be business confidentiality. Thus, when evaluating the amount of a personal credit, the problem of "data islanding" is encountered, and it is difficult to make an accurate estimate of the amount of the personal credit.
Disclosure of Invention
In order to solve the problems, the embodiment of the application provides a training method and a training device for a personal loan amount evaluation model based on a blockchain, which aim to solve the problem of 'data island'.
The embodiment of the application adopts the following technical scheme:
in a first aspect, a training method for a blockchain-based personal loan amount assessment model is provided, the blockchain including a task issuing node and a plurality of training nodes, the method comprising:
Each training node writes respective training information into the blockchain according to the training invitation sent by the task issuing node, wherein the training information comprises training capacity information and user information;
The task issuing node determines one of the training nodes as a central training node according to training information of each training node, sends training tasks to the central training node, and takes the rest of the training nodes as participating training nodes;
The central training node divides the training task into a plurality of training subtasks according to the training capability information of each participating training node, and distributes each training subtask to the corresponding participating training node, so that each participating training node trains according to the distributed training subtasks and based on the respective user information to obtain a part of training model;
And the central training node integrates the part of training models obtained by the participating training nodes and the input layer and the output layer which are deployed at the central training node to obtain a personal loan amount assessment model.
Optionally, the method further comprises:
And the central training node sends the obtained personal loan amount evaluation model to each participating training node so that each participating training node evaluates the personal loan amount based on the personal loan amount evaluation model.
Optionally, the task publishing node determines one from the plurality of training nodes as a central training node according to training information of each training node, and includes:
The task issuing node determines the training evaluation value of each training node according to the training task and the training capability information of each training node;
and taking the training node with the lowest training evaluation value as a central training node.
Optionally, the task publishing node determines a training evaluation value of each training node according to the training task and training capability information of each training node, including:
determining a computational power demand score and a storage capacity demand score of the training task, wherein the sum of the computational power demand score and the storage capacity demand score is one;
determining a calculation power score and a storage capacity score of each training node, wherein the sum of the calculation power score and the storage capacity score is one;
determining a first product of the calculated force demand score and the calculated force score, and a second product of the storage capacity demand score and the storage capacity score, and taking the sum of the first product and the second product as a training evaluation score of each training node.
Optionally, the training task includes a multi-layer architecture personal loan amount assessment model;
The central training node divides the training task into a plurality of training subtasks according to the training capability information of each participating training node, and the central training node comprises:
The central training node determines the training evaluation value of each participating training node according to the training task and the training capability information of each participating training node;
determining the training layer number of each participating training node according to the training evaluation value of each participating training node and the total model layer number of the personal loan amount evaluation model;
And dividing the personal loan amount evaluation model into a plurality of training subtasks according to the training layer numbers of each participating training node.
Optionally, each of the participating training nodes trains based on the respective user information according to the assigned training subtasks to obtain a partial training model, including:
And each participating training node trains the output of the previous participating training node as the input of the subsequent participating training node according to the order of the model training layer in the assigned training subtasks in the personal credit amount evaluation model, and based on the local user information of each participating training node, so as to obtain a part of training model corresponding to each participating training node.
Optionally, the plurality of training nodes includes a banking training node, a financial institution training node, a medical training node, and a consumption training node.
Optionally, the user information comprises personal credit information, personal base information, personal loan information, personal deposit information and personal expense running water information provided by a bank training node;
personal financial product purchase information provided by the financial institution training node;
personal cases, hospitalization information, and physical examination information provided by the medical training node;
personal consumption information provided by the consumer business, and purchase product information.
In a second aspect, there is provided a training apparatus for a blockchain-based personal loan amount assessment model, the blockchain including a task issuing node and a plurality of training nodes, the training apparatus being deployed in each node of the blockchain, the apparatus comprising:
The writing unit is used for writing respective training information into the block chain according to the training invitation sent by the task issuing node, wherein the training information comprises training capability information and user information;
The task issuing unit is used for determining one training node from the plurality of training nodes as a central training node according to training information of each training node, sending the training task to the central training node, and taking the rest training nodes as participating training nodes;
The task allocation unit is used for dividing the training task into a plurality of training subtasks according to the training capability information of each participating training node, and allocating each training subtask to the corresponding participating training node so that each participating training node trains according to the allocated training subtasks and based on the respective user information to obtain a part of training model;
And the integration unit is used for integrating the part of training models obtained by the training nodes and the input layer and the output layer which are deployed at the central training node to obtain a personal loan amount evaluation model.
In a third aspect, a blockchain is provided, the blockchain including a task publishing node and a plurality of training nodes;
each training node is used for writing respective training information into the block chain according to the training invitation sent by the task issuing node, wherein the training information comprises training capacity information and user information;
The task release node is used for determining one of the training nodes as a central training node according to training information of each training node, sending training tasks to the central training node, and taking the rest of the training nodes as participating training nodes;
The central training node is used for dividing the training task into a plurality of training subtasks according to the training capability information of each participating training node, distributing each training subtask to the corresponding participating training node, and training each participating training node based on the respective user information according to the distributed training subtasks so as to obtain a part of training model;
the central training node is used for integrating the part training model obtained by each participating training node and the input layer and the output layer deployed on the central training node to obtain the personal loan amount assessment model.
In a fourth aspect, embodiments of the application also provide an electronic device comprising a processor, and a memory arranged to store computer executable instructions which, when executed, cause the processor to perform any of the methods described above.
In a fifth aspect, embodiments of the present application also provide a computer-readable storage medium storing one or more programs, which when executed by an electronic device comprising a plurality of application programs, cause the electronic device to perform any of the methods described above.
The above at least one technical scheme adopted by the embodiment of the application can achieve the following beneficial effects:
Based on the block chain technology and the idea of split learning, the training task of the whole personal loan amount assessment model is split into a plurality of training subtasks, the participants participating in the co-building personal loan amount assessment model train according to the subtasks based on the local user personal information of each participant, and finally, part of training models obtained by training each participant are integrated together, so that the whole personal loan amount assessment model can be obtained. The application can coordinate a plurality of participants to build a personal loan amount assessment model together on the premise of not revealing the privacy data of clients, the data and related information of each participant are totally uplink, traceable tamper resistance is realized, the local data of each participant is not separated from the local to finish training, the privacy is ensured, the requirements of model training tasks are met, the training tasks are distributed according to the capability of each participant, the situation that the model training cannot be finished due to insufficient capability of each participant, the situation that the capability redundancy exists due to the excessively strong capability of each participant is avoided, and in addition, the application can dynamically change according to the requirements of each participant and the training tasks to flexibly adjust the deployment and training of the training model.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 illustrates a block chain architecture diagram according to one embodiment of the application;
FIG. 2 illustrates a flow diagram of a training method for a blockchain-based personal loan amount assessment model, in accordance with an embodiment of the application;
FIG. 3 illustrates a schematic diagram of a training device for a blockchain-based personal loan amount assessment model, in accordance with an embodiment of the application;
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The following describes in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.
The application provides a training method of a personal loan amount assessment model based on a blockchain, which is based on the blockchain technology and split learning thought, so that a plurality of participants can train and establish the personal loan amount assessment model together on the basis of the blockchain on the premise of not revealing the privacy data of clients.
FIG. 1 illustrates a block chain architecture diagram according to one embodiment of the present application, but implementation of the present application is not limited to the block chain illustrated in FIG. 1, as long as the block chain system is capable of implementing the training method of the personal loan amount assessment model provided by the present application.
As can be seen from the illustration of FIG. 1, the blockchain 100 illustrated in FIG. 1 includes a task publishing node 101 and a plurality of training nodes, wherein one of the plurality of training nodes is a central training node 102 and the remaining training nodes are participating training nodes 103. And the task issuing node 101 is in communication connection with each training node, and the central training node 102 is in communication connection with each participating training node 103.
It should be noted that each training node may be used as a central training node, or a common participating training node, and the present application is not limited thereto, and indicates that the central training node is different from the reference training node in the tasks that are responsible for model training. As to which training node is the central training node, a determination is made during execution of the present application.
FIG. 2 illustrates a training method of the blockchain-based personal loan amount assessment model in an embodiment of the application, and as can be seen from FIG. 2, the application at least includes steps S210-S240:
step S210, each training node writes respective training information into the blockchain according to the training invitation sent by the task issuing node, wherein the training information comprises training capability information and user information.
First, the task issuing node sends training invitations to training nodes to be co-built with the personal loan amount assessment model, which in some embodiments of the application may include banks, financial institutions, medical institutions, consumer enterprises, and the like, which are in turn referred to as banking training nodes, financial institution training nodes, medical training nodes, consumer training nodes.
After the training nodes receive the training invitation of the task issuing node, the training nodes write the respective training information into the blockchain, the blockchain technology can achieve traceability and tamper resistance of data, the information is written into the blockchain to serve as an endorsement for model training, the reliability of the data is guaranteed, further, the accuracy of the model training data is guaranteed, and the accuracy of the trained personal loan amount assessment model is guaranteed.
In some embodiments of the application, the training information for each training node includes, but is not limited to, training capability information and user information. The training capability information comprises computing power and storage capability of each training node, specifically, the number of cores of a CPU of a server of the training node, the cache size of the server, the memory size and the like. The user information includes, but is not limited to, user information locally stored by each participant, such as personal credit information, personal basic information, personal debit and credit information, personal deposit information, and personal expense flow information provided by a banking training node, personal financial product purchase information provided by a financial institution training node, personal case, hospitalization information, and physical examination information provided by a medical training node, personal consumption information provided by a consuming enterprise, and purchase product information, etc.
In some embodiments of the present application, each training node may further perform secondary confirmation on the training data by transmitting the local user information to the central bank in order of the sizes of the identity IDs and two digits after the identity IDs are transmitted before the model training, and perform anti-counterfeiting on the training data according to the feedback information of the central bank, so as to ensure accuracy of the data.
Step S220, the task release node determines one of the training nodes to serve as a central training node according to training information of each training node, sends the training task to the central training node, and the rest of the training nodes serve as participating training nodes.
The task issuing node selects one node from a plurality of training nodes as a central training node, and takes the training nodes except the central training node as common participating training nodes.
In some embodiments of the present application, the selection of the central training node may be selected randomly, or the training node with the strongest training ability may be selected as the central training node according to the training ability information in the training information of each training node, where the central training node coordinates the whole training process. The central training node needs to be in communication connection with other participating training nodes participating in the training.
After the task issuing node determines the central training node, the training task is sent to the central training node, wherein the training task comprises a structure of a personal loan amount assessment model which is not trained yet, and in some embodiments of the application, the structure of the personal loan amount assessment model is multi-layered.
And step S230, the central training node divides the training task into a plurality of training subtasks according to the training capability information of each participating training node, and distributes each training subtask to the corresponding participating training node so that each participating training node trains according to the distributed training subtasks and based on the respective user information to obtain a part of training model.
After the central training node acquires the training task, the whole training task is divided into a plurality of training subtasks. A plurality of training subtasks are then assigned to each participating training node, and a training subtask is assigned to one participating training node.
The training subtasks can be divided according to the training capacity information of each participating training node, subtasks with high training capacity requirements can be divided and distributed to each participating training node with strong training capacity, and subtasks with low training capacity requirements can be divided and distributed to each participating training node with small training capacity requirements, so that the flexible adjustment and reasonable utilization of the computing resources of each participating training node are realized.
Under the condition that the personal loan amount assessment model is of a multi-layer architecture, for a specific segmentation method of the training subtasks, certain adjacent one or more training layers of the personal loan amount assessment model can be segmented into one training subtask, so that one participating training node only needs to train one model training layer or a plurality of model training layers, the whole model is not required to be trained, and the situation that one training node cannot complete training due to insufficient computing capacity is avoided to a great extent.
Each participating training node performs training based on the local user information according to the assigned training subtasks to obtain a partial training model. Thus, the data of each participant can realize model training without sharing.
While the central training node may or may not be involved in training, in some embodiments of the application, only the input and output layers of the personal loan amount assessment model are typically deployed in the central training node, and are required to be trained.
For a specific method of model training, reference may be made to a machine learning method in the prior art, without application being limiting.
Through training, each participating training node obtains a part of the personal loan amount evaluation model, marks the part of the personal loan amount evaluation model as a part of the training model, and each participating training node can write the obtained part of the training model into the blockchain.
And step 240, the central training node integrates the part of training models obtained by the participating training nodes and the input layer and the output layer deployed on the central training node to obtain a personal loan amount evaluation model.
And finally, the central training node integrates the part of training models obtained by the participating training nodes and the input layer and the output layer which are deployed at the central training node together to obtain the whole personal loan amount assessment model, and the personal loan amount assessment model can be used for assessing the personal loan amount.
For the acquisition of part of the training model, the central training node can be acquired from each participating training node, and also can be acquired from the blockchain. For the specific method of integration, the central training node may adjust the initial loan amount assessment model parameters to be consistent with the parameters of the respective portion of the training model.
In some embodiments of the present application, the central training node further evaluates the personal loan amount evaluation model when integrated therewith, and if the accuracy meets the preset requirement, the central training node ends the training to obtain a final personal loan amount evaluation model, and if the accuracy does not meet the preset requirement, the central training node may perform multiple training until the final preset requirement is met.
As can be seen from the method shown in FIG. 2, the training task of the whole personal loan amount assessment model is split into a plurality of training subtasks based on the block chain technology block chain and the split learning idea, the participants participating in the co-building personal loan amount assessment model train according to the subtasks based on the local user personal information of each participant, and finally, the training models obtained by the training of each participant are integrated together to obtain the whole personal loan amount assessment model. The application can coordinate a plurality of participants to build a personal loan amount assessment model together on the premise of not revealing the privacy data of clients, the data of each participant and related information are all uplink, traceable tamper resistance is realized, the local data of each participant is not separated from the local to finish training, the privacy is ensured, the requirements of model training tasks are met, the training tasks are distributed according to the capabilities of each participant, the situation that the model training cannot be finished due to insufficient capabilities of each participant, and the situation that the capability redundancy exists due to the excessively strong capabilities of the participants is avoided, and in addition, the application can dynamically change according to the requirements of each participant and the training tasks to flexibly adjust the deployment and training of the training model.
In some embodiments of the present application, the method further comprises the central training node transmitting the obtained personal loan amount assessment model to each of the participating training nodes, such that each of the participating training nodes assesses the personal loan amount based on the personal loan amount assessment model.
The personal loan amount assessment model may be deployed in systems like banks, financial institutions, etc. for assessing the personal loan amount.
For evaluation of the personal loan amount, the staff can input the personal information of the user to be loaned, and the personal loan amount evaluation model can automatically simulate the personal loan amount through the personal information.
In some embodiments of the application, the task issuing node determines one of the plurality of training nodes as a central training node according to training information of each training node, and the task issuing node determines training evaluation values of the training nodes according to training tasks and training capability information of the training nodes, and takes the training node with the lowest training evaluation value as the central training node.
The central training node needs to be responsible for overall integration work and the like of the whole training process, so that the central training node can have certain computing power and storage capacity and has the highest matching degree with training tasks.
When the task issuing node selects a central training node from a plurality of training nodes, how to select the most suitable training node as the central training node. Some embodiments of the application recommend methods characterized by employing a training evaluation score, a lower training evaluation score indicating that the training node is more suitable as a central training node and a higher training evaluation score indicating that the training node is less suitable as a central training node.
In some embodiments of the present application, the training evaluation score includes two parts, one part is a calculation power demand score and a storage power demand score of the training task, the larger the calculation power demand score or the storage power demand score is, the larger the demand of the training task on the aspect is, and the other part is a calculation power score and a storage power score of the training node, the larger the calculation power score or the storage power score is, the stronger the capability of the training node in this aspect is.
The task issuing node determines a training evaluation score of each training node according to the training task and the training capability information of each training node, and comprises the steps of determining a computing power demand score and a storage capability demand score of the training task, wherein the sum of the computing power demand score and the storage capability demand score is one, determining a computing power score and a storage capability score of each training node, wherein the sum of the computing power score and the storage capability score is one, determining a first product of the computing power demand score and the computing power score, and a second product of the storage capability demand score and the storage capability score, and taking the sum of the first product and the second product as the training evaluation score of each training node. Since the above scores are all
The lower the training evaluation value of one training node is, the higher the matching degree of the training node and the training task is, and finally the training node with the lower training evaluation value is selected as the central training node.
In some embodiments of the present application, the training task includes a multi-layer architecture individual loan amount assessment model, the central training node divides the training task into a plurality of training subtasks according to training capability information of each participating training node, the central training node determines training assessment scores of each participating training node according to the training task and the training capability information of each participating training node, determines a training layer number of each participating training node according to the training assessment scores of each participating training node and a total model layer number of the individual loan amount assessment model, and divides the individual loan amount assessment model into a plurality of training subtasks according to the training layer number of each participating training node.
The central training node may also refer to the "training evaluation value" method described above when dividing the training task into subtasks. Firstly, determining a training evaluation value of a participated training node, wherein the training evaluation value is a decimal greater than zero and less than 1, multiplying the training evaluation value by the total model layer number of a personal loan amount evaluation model to obtain the trainable model layer number of the participated training node, dividing the personal loan amount evaluation model into a plurality of training subtasks according to the calculated model layer number, and one training subtask comprises one layer or a plurality of layers. It should be noted that, when calculating, if the number of model layers that can be trained by one of the participating training nodes is calculated as a non-integer, a rounding method may be performed to calculate the number of model layers of the participating training node.
The training evaluation values of the participating training nodes can be determined by the method described above, and are not described in detail herein.
In some embodiments of the present application, each of the participating training nodes performs training based on the user information of each of the participating training nodes according to the assigned training subtasks to obtain a partial training model, including training each of the participating training nodes by using an output of a preceding participating training node as an input of a subsequent participating training node according to an order of the model training layer in the assigned training subtasks in the personal loan amount evaluation model, based on the user information local to each of the participating training nodes to obtain a partial training model corresponding to each of the participating training nodes.
In the task allocation process, which can also be said to be a model deployment process, the input layer and the output layer of the personal loan amount assessment model can be deployed at a central training node, the central training node trains the input layer and the output layer, and specifically, the central training node can input local user information including, but not limited to, personal basic information, credit information, personal loan information, personal deposit information, personal expense running water information and the like as model input information to the input layer for training. Other participating training nodes may randomly sort and sequentially obtain untrained individual loan amount assessment model structures of corresponding layers for training.
When training is performed, training is performed according to the ordering of the participating training nodes, namely, the personal loan amount evaluation model architecture sequence, the output of the previous participating training node is used as the input of the next participating training node, and the next participating training node receives the output of the previous participating training node, adds the user information in the local data to the output data, and then uses the user information as the input of the participating training node for training. In some embodiments of the application, training may be looped multiple times until the final evaluation criteria are reached, ending the training.
FIG. 3 illustrates a training apparatus for a blockchain-based personal loan amount assessment model, the blockchain including a task issuing node and a plurality of training nodes, the training apparatus being deployed in nodes (101, 102, and 103 of FIG. 1) of the blockchain, as can be seen from FIG. 3, the apparatus 300 includes:
A writing unit 310, configured to write respective training information into the blockchain according to a training invitation sent by the task publishing node, where the training information includes training capability information and user information;
A task publishing unit 320, configured to determine, according to training information of each training node, one of the plurality of training nodes as a central training node, send a training task to the central training node, and the rest as participating training nodes;
the task allocation unit 330 is configured to divide the training task into a plurality of training subtasks according to training capability information of each of the participating training nodes, and allocate each of the training subtasks to a corresponding participating training node, so that each of the participating training nodes performs training according to the allocated training subtasks based on respective user information, so as to obtain a partial training model;
And the integrating unit 340 is configured to integrate the partial training models obtained by the training nodes and the input layer and the output layer deployed at the central training node to obtain a personal loan amount evaluation model.
In some embodiments of the present application, the apparatus further comprises a transmitting unit configured to transmit the obtained personal loan amount assessment model to each participating training node, so that each participating training node assesses the personal loan amount based on the personal loan amount assessment model.
In some embodiments of the present application, in the above apparatus, the task publishing unit 320 is configured to determine a training evaluation score of each training node according to the training task and training capability information of each training node, and use a training node with the lowest training evaluation score as a central training node.
In some embodiments of the present application, in the above apparatus, the task publishing node 320 is configured to determine a computational power demand score and a storage capacity demand score of the training task, where a sum of the computational power demand score and the storage capacity demand score is one, determine a computational power score and a storage capacity score of each training node, where a sum of the computational power score and the storage capacity score is one, determine a first product of the computational power demand score and the computational power score, and a second product of the storage capacity demand score and the storage capacity score, and use a sum of the first product and the second product as a training evaluation score of each training node.
In some embodiments of the present application, in the above apparatus, the training task includes a multi-layer architecture individual loan amount assessment model, the task allocation unit 330 is configured to determine a training assessment score of each of the participating training nodes according to the training task and training capability information of each of the participating training nodes, determine a training layer number of each of the participating training nodes according to the training assessment score of each of the participating training nodes and a total model layer number of the individual loan amount assessment model, and divide the individual loan amount assessment model into a plurality of training subtasks according to the training layer number of each of the participating training nodes.
In some embodiments of the present application, the apparatus further includes a training unit configured to train, in order of the model evaluation model of the model training layer in the assigned training subtask at the personal loan amount, with an output of a preceding participating training node as an input of a subsequent participating training node, based on user information local to each participating training node, to obtain a partial training model corresponding to each participating training node.
In some embodiments of the application, in the above apparatus, the plurality of training nodes includes a banking training node, a financial institution training node, a medical training node, and a consumption training node.
In some embodiments of the present application, in the above-described apparatus, the bank training node provides personal credit information, personal base information, personal debit information, personal credit information, and personal expense flow information, the financial institution training node provides personal financial product purchase information, the medical training node provides personal illness, hospitalization, and physical examination information, and the consumer business provides personal consumption, and purchase product information.
Fig. 4 is a schematic structural view of an electronic device according to an embodiment of the present application. Referring to fig. 4, at the hardware level, the electronic device includes a processor, and optionally an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, network interface, and memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture ) bus, a PCI (PERIPHERAL COMPONENT INTERCONNECT, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 4, but not only one bus or type of bus.
And the memory is used for storing programs. In particular, the program may include program code including computer-operating instructions. The memory may include memory and non-volatile storage and provides instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to form the training device of the personal loan amount assessment model based on the blockchain on a logic level. A processor executing the program stored in the memory, and specifically configured to perform the following operations:
Each training node writes respective training information into the blockchain according to the training invitation sent by the task issuing node, wherein the training information comprises training capacity information and user information;
The task issuing node determines one of the training nodes as a central training node according to training information of each training node, sends training tasks to the central training node, and takes the rest of the training nodes as participating training nodes;
The central training node divides the training task into a plurality of training subtasks according to the training capability information of each participating training node, and distributes each training subtask to the corresponding participating training node, so that each participating training node trains according to the distributed training subtasks and based on the respective user information to obtain a part of training model;
And the central training node integrates the part of training models obtained by the participating training nodes and the input layer and the output layer which are deployed at the central training node to obtain a personal loan amount assessment model.
The method performed by the training device of the blockchain-based personal loan amount assessment model disclosed in the embodiment of fig. 3 of the present application may be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The Processor may be a general-purpose Processor including a central processing unit (Central Processing Unit, CPU), a network Processor (Network Processor, NP), etc., or may be a digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoding processor, or in a combination of hardware and software modules in the decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.
The electronic device may further execute the method executed by the training device of the blockchain-based personal loan amount evaluation model in fig. 3, and implement the functions of the training device of the blockchain-based personal loan amount evaluation model in the embodiment shown in fig. 3, which are not described herein.
The embodiment of the present application also proposes a computer-readable storage medium storing one or more programs, the one or more programs comprising instructions that, when executed by an electronic device comprising a plurality of application programs, enable the electronic device to perform a method performed by a training apparatus of a blockchain-based personal loan amount assessment model in the embodiment shown in fig. 3, and specifically for performing:
Each training node writes respective training information into the blockchain according to the training invitation sent by the task issuing node, wherein the training information comprises training capacity information and user information;
The task issuing node determines one of the training nodes as a central training node according to training information of each training node, sends training tasks to the central training node, and takes the rest of the training nodes as participating training nodes;
The central training node divides the training task into a plurality of training subtasks according to the training capability information of each participating training node, and distributes each training subtask to the corresponding participating training node, so that each participating training node trains according to the distributed training subtasks and based on the respective user information to obtain a part of training model;
And the central training node integrates the part of training models obtained by the participating training nodes and the input layer and the output layer which are deployed at the central training node to obtain a personal loan amount assessment model.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may be implemented in any method or technology for information storage. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (8)
1. A method of training a blockchain-based personal loan amount assessment model, the blockchain comprising a task issuing node and a plurality of training nodes, the method comprising:
each training node writes respective training information into the blockchain according to the training invitation sent by the task issuing node, wherein the training information comprises training capacity information and user information;
The task issuing node determines one of the training nodes as a central training node according to training information of each training node, sends training tasks to the central training node, and takes the rest training nodes as participating training nodes;
the central training node divides the training task into a plurality of training subtasks according to the training capability information of each participating training node, and distributes each training subtask to the corresponding participating training node, so that each participating training node trains according to the distributed training subtasks and based on the respective user information to obtain a part of training model;
the central training node integrates the part of training models obtained by each participating training node and the input layer and the output layer which are deployed at the central training node to obtain a personal loan amount evaluation model;
each participating training node performs training based on respective user information according to the assigned training subtasks to obtain a partial training model, including:
and each participating training node trains the user information local to the following participating training node as the input of the following participating training node after adding the user information local to the following participating training node to the output of the preceding participating training node according to the sequence of the model training layer in the assigned training subtask in the personal loan amount evaluation model, so as to obtain a part of training model corresponding to each participating training node.
2. The method according to claim 1, wherein the method further comprises:
And the central training node sends the obtained personal loan amount evaluation model to each participating training node so that each participating training node evaluates the personal loan amount based on the personal loan amount evaluation model.
3. The method of claim 1, wherein the task distribution node determines one of the plurality of training nodes as a central training node based on training information of each training node, comprising:
the task issuing node determines the training evaluation value of each training node according to the training task and the training capability information of each training node;
and taking the training node with the lowest training evaluation value as a central training node.
4. A method according to claim 3, wherein the task publishing node determines a training assessment score for each training node based on the training task and training capability information for each training node, comprising:
Determining a computational power demand score and a storage capacity demand score of the training task, wherein the sum of the computational power demand score and the storage capacity demand score is 1;
Determining a calculation power score and a storage capacity score of each training node, wherein the sum of the calculation power score and the storage capacity score is 1;
determining a first product of the calculated power demand score and the calculated power score, and a second product of the storage power demand score and the storage power score, and taking the sum of the first product and the second product as a training evaluation score of each training node.
5. The method of claim 1, wherein the training task comprises a multi-tiered personal loan amount assessment model;
the central training node divides the training task into a plurality of training subtasks according to the training capability information of each participating training node, and the central training node comprises:
The central training node determines the training evaluation value of each participating training node according to the training task and the training capability information of each participating training node;
determining the training layer number of each participating training node according to the training evaluation value of each participating training node and the total model layer number of the personal loan amount evaluation model;
And dividing the personal loan amount evaluation model into a plurality of training subtasks according to the training layer numbers of each participating training node.
6. The method of any one of claims 1-5, wherein the plurality of training nodes comprises a banking training node, a financial institution training node, a medical training node, and a consumption training node.
7. The method of claim 6, wherein the user information comprises personal credit information, personal base information, personal debit information, personal credit information, and personal expense flow information provided by a banking training node;
personal financial product purchase information provided by the financial institution training node;
personal cases, hospitalization information, and physical examination information provided by the medical training node;
personal consumption information and purchase product information provided by the consumption training node.
8. A training device for a blockchain-based personal loan amount assessment model, wherein the blockchain includes a task issuing node and a plurality of training nodes, the training device being deployed in each node of the blockchain, the device comprising:
The writing unit is used for writing respective training information into the block chain according to the training invitation sent by the task issuing node, wherein the training information comprises training capacity information and user information;
The task issuing unit is used for determining one training node from the plurality of training nodes as a central training node according to training information of each training node, sending the training task to the central training node, and taking the rest training nodes as participating training nodes;
The task allocation unit is used for dividing the training task into a plurality of training subtasks according to the training capability information of each participating training node, and allocating each training subtask to the corresponding participating training node so that each participating training node trains according to the allocated training subtasks and based on the respective user information to obtain a part of training model;
the integration unit is used for integrating the part of training models obtained by each participating training node and the input layer and the output layer which are deployed at the central training node to obtain a personal loan amount evaluation model;
The training unit is used for training the local user information of the following participating training nodes as the input of the following participating training nodes after being added to the output of the preceding participating training nodes according to the order of the model training layer in the assigned training subtask in the personal loan amount evaluation model, so as to obtain the partial training model corresponding to each participating training node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111245698.XA CN114298817B (en) | 2021-10-26 | 2021-10-26 | Training method and device for personal loan amount assessment model based on blockchain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111245698.XA CN114298817B (en) | 2021-10-26 | 2021-10-26 | Training method and device for personal loan amount assessment model based on blockchain |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114298817A CN114298817A (en) | 2022-04-08 |
| CN114298817B true CN114298817B (en) | 2025-10-14 |
Family
ID=80964588
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111245698.XA Active CN114298817B (en) | 2021-10-26 | 2021-10-26 | Training method and device for personal loan amount assessment model based on blockchain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114298817B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4515387A1 (en) * | 2022-04-25 | 2025-03-05 | Telefonaktiebolaget LM Ericsson (publ) | Methods and apparatus for computing resource allocation |
| CN117217719B (en) * | 2023-11-07 | 2024-02-09 | 湖南海润天恒科技集团有限公司 | An intelligent management method and system for talent information recruitment data based on big data |
| CN117992223B (en) * | 2024-01-31 | 2024-11-26 | 三六零数字安全科技集团有限公司 | Model training method, device, electronic device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111949395A (en) * | 2020-07-16 | 2020-11-17 | 广州玖的数码科技有限公司 | Block chain-based shared computing power data processing method, system and storage medium |
| CN112328617A (en) * | 2020-11-19 | 2021-02-05 | 杭州趣链科技有限公司 | Learning mode parameter updating method for longitudinal federal learning and electronic device |
| CN112949853A (en) * | 2021-02-23 | 2021-06-11 | 北京金山云网络技术有限公司 | Deep learning model training method, system, device and equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11296935B2 (en) * | 2016-12-30 | 2022-04-05 | Intel Corporation | Service provision to IoT devices |
| CN112215608B (en) * | 2019-01-18 | 2024-08-09 | 创新先进技术有限公司 | Data processing method and device |
| CN111339553A (en) * | 2020-02-14 | 2020-06-26 | 云从科技集团股份有限公司 | Task processing method, system, device and medium |
| CN111932367A (en) * | 2020-08-13 | 2020-11-13 | 中国银行股份有限公司 | Pre-credit evaluation method and device |
-
2021
- 2021-10-26 CN CN202111245698.XA patent/CN114298817B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111949395A (en) * | 2020-07-16 | 2020-11-17 | 广州玖的数码科技有限公司 | Block chain-based shared computing power data processing method, system and storage medium |
| CN112328617A (en) * | 2020-11-19 | 2021-02-05 | 杭州趣链科技有限公司 | Learning mode parameter updating method for longitudinal federal learning and electronic device |
| CN112949853A (en) * | 2021-02-23 | 2021-06-11 | 北京金山云网络技术有限公司 | Deep learning model training method, system, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114298817A (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114298817B (en) | Training method and device for personal loan amount assessment model based on blockchain | |
| US11087372B2 (en) | Benefit allocation method, apparatus, and electronic device | |
| US10657526B2 (en) | System and method to dynamically setup a private sub-blockchain based on agility of transaction processing | |
| TWI687876B (en) | Method and device for virtual resource allocation, model establishment, data prediction | |
| Cai et al. | Fair allocation through selective information acquisition | |
| CN113159190B (en) | Federal incentive distribution methods, devices, computer equipment and storage media | |
| WO2021103909A1 (en) | Risk prediction method and apparatus, risk prediction model training method and apparatus, and electronic device | |
| CN114219338A (en) | Resource allocation method and device based on joint learning | |
| CN110009497B (en) | Block chain-based decision-making method and device and electronic equipment | |
| TW202008228A (en) | Event prediction method and apparatus and electronic device | |
| CN115564594A (en) | Financial product recommendation method and device based on big data analysis | |
| CN114817209A (en) | Processing method and device, processor and electronic device for monitoring rules | |
| CN103064955A (en) | Inquiry planning method and device | |
| CN111325557B (en) | A method, device and equipment for detecting merchant risk | |
| CN114546636B (en) | A data interaction system and decentralized edge model training and verification method | |
| Li et al. | A dynamic pricing reverse auction‐based resource allocation mechanism in cloud workflow systems | |
| CN107194712B (en) | Method and device for recording change information of shared account and method and system for supplementing account of internal account | |
| CN120672031A (en) | Prize distribution method, device, computer equipment and storage medium | |
| CN112087518B (en) | Consensus method, apparatus, computer system, and medium for blockchains | |
| CN113312184A (en) | Service data processing method and related equipment | |
| CN107018158B (en) | Method and device for screening Internet resources | |
| CN120045308A (en) | Multi-head attention calculation self-adaptive distribution method and device of transducer model | |
| TWI706341B (en) | Event prediction method and device, electronic equipment | |
| Esteban | The social viability of money: competitive equilibria and the core of overlapping generations economies | |
| CN116932218A (en) | Memory information determination method, device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |